{"id":"https://openalex.org/W4388233464","doi":"https://doi.org/10.1145/3581783.3612485","title":"SpeechTripleNet: End-to-End Disentangled Speech Representation Learning for Content, Timbre and Prosody","display_name":"SpeechTripleNet: End-to-End Disentangled Speech Representation Learning for Content, Timbre and Prosody","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388233464","doi":"https://doi.org/10.1145/3581783.3612485"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612485","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612485","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612485","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612485","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101486499","display_name":"Hui Lu","orcid":"https://orcid.org/0000-0002-7698-6262"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hui Lu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-7698-6262","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-9543-1572","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8533-0524","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-4427-3532","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0889,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80143391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2829","last_page":"2837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8497250080108643},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7609834671020508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7278150916099548},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6874849200248718},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46553197503089905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43042951822280884},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4103173315525055},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37316328287124634}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8497250080108643},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7609834671020508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278150916099548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6874849200248718},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46553197503089905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43042951822280884},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4103173315525055},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37316328287124634},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612485","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612485","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612485","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612485","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612485","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612485","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388233464.pdf","grobid_xml":"https://content.openalex.org/works/W4388233464.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1735538598","https://openalex.org/W2560674852","https://openalex.org/W2626699878","https://openalex.org/W2747329762","https://openalex.org/W2753738274","https://openalex.org/W2904459034","https://openalex.org/W3015434413","https://openalex.org/W3092028330","https://openalex.org/W4312732823","https://openalex.org/W4319862209"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"Disentangled":[0],"speech":[1,12,21,32,38,61,115,155,174,180],"representation":[2],"learning":[3,104,150],"aims":[4],"to":[5,59,85,94,113,142],"separate":[6],"different":[7,183],"factors":[8,98],"of":[9,52,55,130,137],"variation":[10],"from":[11],"into":[13,22,68,116],"disjoint":[14],"representations.":[15,72],"This":[16,106],"paper":[17,107],"focuses":[18],"on":[19,42,124],"disentangling":[20],"representations":[23,117],"for":[24,37,118],"three":[25,97],"factors:":[26],"spoken":[27,44],"content,":[28,119],"speaker":[29,47,71,80],"timbre,":[30,120],"and":[31,46,64,121,134,157,163],"prosody.":[33,122],"Many":[34],"previous":[35],"methods":[36,76,93],"disentanglement":[39],"have":[40,77],"focused":[41],"separating":[43],"content":[45,69],"timbre.":[48],"However,":[49],"the":[50,128,131,135],"lack":[51],"explicit":[53,79],"modeling":[54],"prosodic":[56],"information":[57,138],"leads":[58],"degraded":[60],"generation":[62],"performance":[63],"uncontrollable":[65],"prosody":[66],"leakage":[67],"and/or":[70],"While":[73],"some":[74],"recent":[75],"utilized":[78],"labels":[81],"or":[82,102],"pre-trained":[83],"models":[84],"facilitate":[86],"triple-factor":[87,173],"disentanglement,":[88,175],"there":[89],"are":[90],"no":[91,158],"end-to-end":[92,111],"simultaneously":[95],"disentangle":[96,114],"using":[99],"only":[100,153],"unsupervised":[101],"self-supervised":[103],"objectives.":[105],"introduces":[108],"SpeechTripleNet,":[109],"an":[110],"method":[112,151],"Based":[123],"VAE,":[125],"SpeechTripleNet":[126,168],"restricts":[127],"structures":[129],"latent":[132],"variables":[133],"amount":[136],"captured":[139],"in":[140,171],"them":[141],"induce":[143],"disentanglement.":[144],"It":[145],"is":[146,169],"a":[147],"pure":[148],"unsupervised/self-supervised":[149],"that":[152,167],"requires":[154],"data":[156],"additional":[159],"labels.":[160],"Our":[161],"qualitative":[162],"quantitative":[164],"results":[165],"demonstrate":[166],"effective":[170],"achieving":[172],"as":[176,178],"well":[177],"controllable":[179],"editing":[181],"concerning":[182],"factors.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}